Open3D (C++ API)  0.18.0+80ae047
Functions
open3d::geometry::keypoint Namespace Reference

Functions

std::shared_ptr< PointCloudComputeISSKeypoints (const PointCloud &input, double salient_radius=0.0, double non_max_radius=0.0, double gamma_21=0.975, double gamma_32=0.975, int min_neighbors=5)
 Function that computes the ISS Keypoints from an input point cloud. This implements the keypoint detection module proposed in Yu Zhong ,"Intrinsic Shape Signatures: A Shape Descriptor for 3D Object Recognition", 2009. The implementation is inspired by the PCL one. More...
 

Function Documentation

◆ ComputeISSKeypoints()

std::shared_ptr< PointCloud > open3d::geometry::keypoint::ComputeISSKeypoints ( const PointCloud input,
double  salient_radius = 0.0,
double  non_max_radius = 0.0,
double  gamma_21 = 0.975,
double  gamma_32 = 0.975,
int  min_neighbors = 5 
)

Function that computes the ISS Keypoints from an input point cloud. This implements the keypoint detection module proposed in Yu Zhong ,"Intrinsic Shape Signatures: A Shape Descriptor for 3D Object Recognition", 2009. The implementation is inspired by the PCL one.

Parameters
inputThe input PointCloud where to compute the ISS Keypoints.
salient_radiusThe radius of the spherical neighborhood used to detect the keypoints
non_max_radiusThe non maxima suppression radius. If non of the input parameters are specified or are 0.0, then they will be computed from the input data, taking into account the Model Resolution.
gamma_21The upper bound on the ratio between the second and the first eigenvalue
gamma_32The upper bound on the ratio between the third and the second eigenvalue
min_neighborsMinimum number of neighbors that has to be found to consider a keypoint.
Authors
Ignacio Vizzo and Cyrill Stachniss, University of Bonn.